RESEARCH & DEVELOPMENT
Measure first,
then build.
Our research practice tests ideas against real data before they become client systems: prototypes, evaluations, and written findings.
METHOD
How a question
becomes a system.
Every research track follows the same four steps, with a written decision at the end.
- STEP 1
Frame the question
State what we want to learn, what result would change a decision, and how we will measure it.
- STEP 2
Prototype
Build the smallest thing that can answer the question with real or realistic data.
- STEP 3
Evaluate
Run it against a fixed test set, record results, and compare with a simple baseline.
- STEP 4
Decide and document
Ship, iterate, or stop. The finding is written up whichever way it goes.
RESEARCH AREAS
What we are
working on.
Areas where we invest research time, with the methods we use.
Agent reliability
How multi-step AI workflows fail, and which retries, checks, and approvals catch failures before customers see them.
Retrieval quality
Measuring when answers grounded in company documents are correct, cited, and current.
Secure integrations
Least-privilege patterns for connecting AI and automation to business systems.
Operational data models
Schemas for dispatch, quoting, and billing that hold up across many companies.
Voice and messaging
Latency, turn-taking, and handoff design for phone and SMS assistants.
Cost and performance
Keeping AI and infrastructure costs predictable as usage grows.
LAB NOTES
Recent
writing.
Practical findings from the work, published in Insights.
Putting AI agents to work without losing control
Where agents help, where people must stay in the loop.
SECURITYPassing your first enterprise security review
The controls that answer most questionnaires.
OPERATIONSWhen to replace the spreadsheet that runs your business
Signs you have outgrown it, and how to move.
Have a hard technical question?
We run short research sprints to answer it before you commit to a build.
